as.mvLSW: Multivariate Locally Stationary Wavelet Object

Description

Constructs a multivariate locally stationary wavelet (mvLSW) object.

Usage

as.mvLSW(x, filter.number = 1, family = "DaubExPhase",
    smooth.type = "all", smooth.kernel = kernel("daniell", 0), 
    bias.correct = FALSE, min.eig.val = -Inf, names = NULL)
  
  is.mvLSW(object)

Arguments

4D array of order PxPxJxT where P is the number of signals of the time series of length T such that T=\(2^J\) for some positive integer J defining the levels of the mvLSW object.

family

Specifies the family of wavelet. Only two options are available, either "DaubExPhase" (default) or "DaubLeAsymm".

filter.number

Integer number defining the number of vanishing moments of the wavelet function. By default, filter.number=1 and so defining the Haar wavelet.

smooth.type

What type of smoothing regime has been applied. Either "all" (default) if the smoothing method been applied to all levels. Otherwise "by.level", a different smoothing method is applied to each level.

smooth.kernel

Definition of the smoothing kernel from kernel(). By default, the identity kernel is defined.

bias.correct

Logical, has a bias correction been applied to the data. FALSE by default.

min.eig.val

Minimum eigenvalue from spectral matrices across all levels and locations, set at -Inf by default. If NA, then the minimum eigenvalue is calculated.

names

Character vector containing the signal names of the multivariate time series.

object

An R object.

Value

The as.mvLSW command invisibly returns a list with the following items:

spectrum

A 4D array containing the data relating to the estimate of interest.

Information

List containing information about the estimate relating to the methodology.

The list Information contains:

names

Character vector containing the signal names.

dimensions

A list containing items P - the number of signals forming of the time series, T - the length of the time series and J - the number of levels in the wavelet transform of the data.

wavelet

A list containing the filter.number and family of the wavelet used in the transformation.

smooth

A list containing information about the smoothing applied to the estimate. Items of the list are: smooth.type - name of the smoothing regime, smooth.kernels - a tskernel class from the command kernel, GCV - generalized cross-validation gamma deviance criterion of the smoothing and smooth.eps - smoothing threshold. If smooth.type="by.level", then smooth.kernels is a list containing the tskernel object for each level from fine to coarse. In addition, GCV is a length J vector containing the criterion estimate for each level from fine to coarse.

correction

A list containing bias.correction and min.eig.val.

The command is.mvLSW returns TRUE if the supplied object is a mvLSW object as described above. Otherwise, the command returns FALSE.

Details

as.mvLSW constructs a multivariate locally stationary classed object that contains all information about the constructions of various multivariate wavelet estimates.

The command is.mvLSW checks that the supplied R object is a valid mvLSW object in that its structure and contents are as expected.

Examples

Run this code

# NOT RUN {
## Define evolutionary wavelet spectrum, structure only on level 2
Spec <- array(0, dim = c(3, 3, 8, 256))
Spec[1, 1, 2, ] <- 10
Spec[2, 2, 2, ] <- c(rep(5, 64), rep(0.6, 64), rep(5, 128))
Spec[3, 3, 2, ] <- c(rep(2, 128), rep(8, 128))
Spec[2, 1, 2, ] <- Spec[1, 2, 2, ] <- c(rep(0, 64), seq(0, 1, len = 128), rep(1, 64))
Spec[3, 1, 2, ] <- Spec[1, 3, 2, ] <- c(rep(-1, 128), rep(5, 128))
Spec[3, 2, 2, ] <- Spec[2, 3, 2, ] <- -0.5

## Define EWS as mvLSW object
EWS <- as.mvLSW(x = Spec, filter.number = 1, family = "DaubExPhase", 
  names = c("A", "B", "C"), min.eig.val = NA)
is.mvLSW(EWS)
plot(EWS, style = 2, info = 2)
# }